ENGN 1610 Image Understanding

Pedro Felzenszwalb
Email: pff (at) brown.edu

Lectures: T/Th 10:30-11:50 PM Barus & Holley 751

Office hours: Monday 2-3 PM

Course description
Image processing is a technology experiencing explosive growth; it is central to medical image analysis and transmission, industrial inspection, image enhancement, indexing into pictorial and video databases, e.g., WWW, and to robotic vision, face recognition, and image compression. This senior-level undergraduate course covers theoretical underpinnings of this field and includes a series of practical MATLAB image processing projects. ENGN 1570 is recommended but not required.

Image formation
Low-level image processing
3D reconstruction
Motion estimation
Image segmentation
Object recognition

Computer Vision: Algorithms and Applications. Szeliski. Springer.
A draft PDF is available here.


Topic 1: Image Formation
Topic 2: Image Filtering and Edge detection
Topic 3: Multiview geometry and stereo matching
Topic 4: Image Segmentation
Topic 5: Graph algorithms
Topic 6: Template matching
Topic 7: Convolutional Neural Networks
Topic 8: Geometric Methods for Recognition
Topic 9: Motion and Optical flow

Readings Assignments

1) Szeliski chapter 2
2) Edge detection Handout and Additional examples
3) Mean shift and feature space analysis
4) Dynamic Programming and Graph Algorithms
5) Object Detection
6) LeNet paper (pages 1 to 11)
7) AlexNet paper
8) Optical flow review paper
9) Dense Optical flow paper


Using images in MATLAB: example.m

Assignment 1 and test images
Due: Wednesday February 19

Assignment 2 and test images
Due: Monday March 9

Assignment 3 and files
Due: Monday March 9

Assignment 4 and data
Due: Friday May 1